Question Answering On Tempquestions
평가 지표
F1
Hits@1
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | F1 | Hits@1 | Paper Title | Repository |
|---|---|---|---|---|
| SF-TQA | 41.1 | 41.2 | Semantic Framework based Query Generation for Temporal Question Answering over Knowledge Graphs | - |
| QUINT | 28.8 | 27 | QUINT: Interpretable Question Answering over Knowledge Bases | - |
| QAap | 68.1 | - | Question Answering as Programming for Solving Time-Sensitive Questions | |
| Few-shot gpt-3.5-turbo CoT | 60.1 | - | - | - |
| QUINT+TEQUILA | 32 | 31.7 | TEQUILA: Temporal Question Answering over Knowledge Bases | - |
| Fine-tune | 44.6 | - | - | - |
| AQQU+TEQUILA | 37.5 | 36.2 | TEQUILA: Temporal Question Answering over Knowledge Bases | - |
| AQQU | 27.2 | 24.9 | More Accurate Question Answering on Freebase |
0 of 8 row(s) selected.